GPT-4O
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective.
Input
Output
Context
128K
Max Output
16K
Parameters
—
Technical Specifications
Model TypeChat
Context Window128K
Max Output Tokens16K
Parameters—
Training Cutoff—
Licenseproprietary
Capabilities
Input Modalities
textimagefile
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningstreamingsystem_promptstext_generationtool_usevision
Benchmarks
2.9%
HLE
11.7%
AIME
52.1%
GPQA
33.1%
SciCode
79.5%
MATH 500
16.6
Coding
31.7%
LiveCodeBench
18.6
Intelligence
113
Speed (tok/s)
0.693
TTFA (s)
0.693
TTFT (s)
Resources & Links
proprietary — Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.